← back to catalog · registered 2026-11-19 20:04

nulliaukamk/nullabby1.5-uncensored

nulliaukamk multimodal
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/nulliaukamk%2Fnullabby1.5-uncensored"
Response includes
  • classification m1
  • files 13
  • author_summary 2 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

No other method signals detected in this model.
Confidence
MEDIUM
Why this label 3 signals
Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.
  • 'abliterated' in name/tags
  • is_gguf=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
Downloads · 30-day
43
Likes
0
Descendants
1
in 1 direct fork
Model age
2d ago
created 2026-11-19
Downloads over time
Now 43 → from 0 ↑ 0%
0163247 0 on Nov 19 43 on Nov 22 Nov
Nov 19 → Nov 22 · 4 snapshots · spans 3 days

Genealogy 1 direct fork

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

Metadata

License
apache-2.0
Languages
en
Tags
transformers safetensors qwen3_5 image-text-to-text text-generation-inference unsloth heretic uncensored decensored abliterated reproducible conversational

Related

Total size
17.5 GB
Files
13
Quantizations
1
Registered
2026-11-19 20:04
Last updated on HF
2026-11-19 19:24

Files by quantization

Auxiliary files 13 files 17.5 GB
model-00002-of-00004.safetensors 4.65 GB 6e65bab7 download
model-00003-of-00004.safetensors 4.61 GB d80b6362 download
model-00001-of-00004.safetensors 4.60 GB fe5cfde7 download
model-00004-of-00004.safetensors 3.66 GB 1260ab42 download
tokenizer.json 19.1 MB a5cd9732 download
model.safetensors.index.json 67.6 KB 778b7bbb download
chat_template.jinja 7.57 KB a585dec8 download
config.json 2.91 KB f8a214ab download
.gitattributes 1.53 KB 52373fe2 download
README.md 1.53 KB d3dad5ad download
processor_config.json 1.19 KB 43c4343e download
tokenizer_config.json 1.19 KB 86148f3d download
generation_config.json 142 B ab8366fb download

README current version from Hugging Face


base_model: nulliaukamk/nullabby1.5-merged
tags:

  • text-generation-inference
  • transformers
  • unsloth
  • qwen3_5
  • heretic
  • uncensored
  • decensored
  • abliterated
  • reproducible
    license: apache-2.0
    language:
  • en

This is a decensored version of nulliaukamk/nullabby1.5-merged, made using Heretic v2.1.0

[!TIP]
This model is reproducible!

See the README in the reproduce directory for more information.

Arbitrary-Rank Ablation (ARA) parameters

Parameter Value
start_layer_index 5
end_layer_index 22
preserve_good_behavior_weight 0.8811
steer_bad_behavior_weight 0.0109
overcorrect_relative_weight 0.7735
neighbor_count 13

Performance

Metric This model Original model (nulliaukamk/nullabby1.5-merged)
Refusals 0/100 84/100
KL divergence 0.0760 0 (by definition)

Uploaded finetuned model

  • Developed by: nulliaukamk
  • License: apache-2.0
  • Finetuned from model : Qwen/Qwen3.5-9B

This qwen3_5 model was trained 2x faster with Unsloth and Huggingface's TRL library.

README history 2 versions

The author's README evolved over time. Click a version to see its content at that point.

  1. 2026-11-19 Upload README.md with huggingface_hub 0b57b17 1.5 KB
    Loading...
  2. 2026-11-19 Upload Qwen3_5ForConditionalGeneration 9aba0f3 5.1 KB
    Loading...
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Open in Abliteration